Estimation of modified Zernike coefficients from turbulence-degraded multispectral imagery using deep learning.

We investigate how wavelength diversity affects the performance of a deep-learning model that predicts the modified Zernike coefficients of turbulence-induced wavefront error from multispectral images. The ability to perform accurate predictions of the coefficients from images collected in turbulent conditions has potential applications in image restoration. The source images for this work were a point object and extended objects taken from a character-based dataset, and a wavelength-dependent simulation was developed that applies the effects of isoplanatic atmospheric turbulence to the images. The simulation utilizes a phase screen resampling technique to emulate the simultaneous collection of each band of a multispectral image through the same turbulence realization. Simulated image data were generated for the point and extended objects at various turbulence levels, and a deep neural network architecture based on AlexNet was used to predict the modified Zernike coefficients. Mean squared error results demonstrate a significant improvement in predicting modified Zernike coefficients for both the point object and extended objects as the number of spectral bands is increased. However, the improvement with the number of bands was limited when using extended objects with additive noise.

Estimation of non-uniform motion blur using a patch-based regression convolutional neural network.

The non-uniform blur of atmospheric turbulence can be modeled as a superposition of linear motion blur kernels at a patch level. We propose a regression convolutional neural network (CNN) to predict angle and length of a linear motion blur kernel for varying sized patches. We analyze the robustness of the network for different patch sizes and the performance of the network in regions where the characteristics of the blur are transitioning. Alternating patch sizes per epoch in training, we find coefficient of determination scores across a range of patch sizes of R 2>0.78 for length and R 2>0.94 for angle prediction. We find that blur predictions in regions overlapping two blur characteristics transition between the two characteristics as overlap changes. These results validate the use of such a network for prediction of non-uniform blur characteristics at a patch level.

Quantifying the Consistency and Characterizing the Confidence of Coronal Holes Detected by Active Contours Without Edges (ACWE).

Coronal Holes (CHs) are regions of open magnetic-field lines, resulting in high-speed solar wind. Accurate detection of CHs is vital for space-weather prediction. This paper presents an intramethod ensemble for coronal-hole detection based on the Active Contours Without Edges (ACWE) segmentation algorithm. The purpose of this ensemble is to develop a confidence map that defines, for all ondisk regions of a solar extreme ultraviolet (EUV) image, the likelihood that each region belongs to a CH based on that region's proximity to, and homogeneity with, the core of identified CH regions. By relying on region homogeneity, and not intensity (which can vary due to various factors, including line-of-sight changes and stray light from nearby bright regions), to define the final confidence of any given region, this ensemble is able to provide robust, consistent delineations of the CH regions. Using the metrics of global consistency error (GCE), local consistency error (LCE), intersection over union (IOU), and the structural similarity index measure (SSIM), the method is shown to be robust to different spatial resolutions maintaining a median IOU >0.75 and minimum SSIM >0.93 even when the segmentation process was performed on an EUV image decimated from 4096×4096 pixels down to 512×512 pixels. Furthermore, using the same metrics, the method is shown to be robust across short timescales, producing segmentation with a mean IOU of 0.826 from EUV images taken at a 1-h cadence, and showing a smooth decay in similarity across all metrics as a function of time, indicating self-consistent segmentations even when corrections for exposure time have not been applied to the data. Finally, the accuracy of the segmentations and confidence maps are validated by considering the skewness (i.e., unipolarity) of the underlying magnetic field.

Solar active region magnetogram image dataset for studies of space weather.

In this dataset we provide a comprehensive collection of line-of-sight (LOS) solar photospheric magnetograms (images quantifying the strength of the photospheric magnetic field) from the National Aeronautics and Space Administration's (NASA's) Solar Dynamics Observatory (SDO). The dataset incorporates data from three sources and provides SDO Helioseismic and Magnetic Imager (HMI) magnetograms of solar active regions (regions of large magnetic flux, generally the source of eruptive events) as well as labels of corresponding flaring activity. This dataset will be useful for image analysis or solar physics research related to magnetic structure, its evolution over time, and its relation to solar flares. The dataset will be of interest to those researchers investigating automated solar flare prediction methods, including supervised and unsupervised machine learning (classical and deep), binary and multi-class classification, and regression. This dataset is a minimally processed, user configurable dataset of consistently sized images of solar active regions that can serve as a comprehensive image dataset of LOS photospheric magnetograms for solar flare prediction research.

Deep learning estimation of modified Zernike coefficients and recovery of point spread functions in turbulence.

Recovering the turbulence-degraded point spread function from a single intensity image is important for a variety of imaging applications. Here, a deep learning model based on a convolutional neural network is applied to intensity images to predict a modified set of Zernike polynomial coefficients corresponding to wavefront aberrations in the pupil due to turbulence. The modified set assigns an absolute value to coefficients of even radial orders due to a sign ambiguity associated with this problem and is shown to be sufficient for specifying the intensity point spread function. Simulated image data of a point object and simple extended objects over a range of turbulence and detection noise levels are created for the learning model. The MSE results for the learning model show that the best prediction is found when observing a point object, but it is possible to recover a useful set of modified Zernike coefficients from an extended object image that is subject to detection noise and turbulence.

Morphological restriction of human coronary artery endothelial cells substantially impacts global gene expression patterns.

Alterations in cell shape have been shown to modulate chromatin condensation and cell lineage specification; however, the mechanisms controlling these processes are largely unknown. Because endothelial cells experience cyclic mechanical changes from blood flow during normal physiological processes and disrupted mechanical changes as a result of abnormal blood flow, cell shape deformation and loss of polarization during coronary artery disease, we aimed to determine how morphological restriction affects global gene expression patterns. Human coronary artery endothelial cells (HCAECs) were cultured on spatially defined adhesive micropatterns, forcing them to conform to unique cellular morphologies differing in cellular polarization and angularity. We utilized pattern recognition algorithms and statistical analysis to validate the cytoskeletal pattern reproducibility and uniqueness of each micropattern, and performed microarray analysis on normal-shaped and micropatterned HCAECs to determine how constrained cellular morphology affects gene expression patterns. Analysis of the data revealed that forcing HCAECs to conform to geometrically-defined shapes significantly affects their global transcription patterns compared to nonrestricted shapes. Interestingly, gene expression patterns were altered in response to morphological restriction in general, although they were consistent regardless of the particular shape the cells conformed to. These data suggest that the ability of HCAECs to spread, although not necessarily their particular morphology, dictates their genomics patterns.

Targeting of beta adrenergic receptors results in therapeutic efficacy against models of hemangioendothelioma and angiosarcoma.

Therapeutic targeting of the beta-adrenergic receptors has recently shown remarkable efficacy in the treatment of benign vascular tumors such as infantile hemangiomas. As infantile hemangiomas are reported to express high levels of beta adrenergic receptors, we examined the expression of these receptors on more aggressive vascular tumors such as hemangioendotheliomas and angiosarcomas, revealing beta 1, 2, and 3 receptors were indeed present and therefore aggressive vascular tumors may similarly show increased susceptibility to the inhibitory effects of beta blockade. Using a panel of hemangioendothelioma and angiosarcoma cell lines, we demonstrate that beta adrenergic inhibition blocks cell proliferation and induces apoptosis in a dose dependent manner. Beta blockade is selective for vascular tumor cells over normal endothelial cells and synergistically effective when combined with standard chemotherapeutic or cytotoxic agents. We demonstrate that inhibition of beta adrenergic signaling induces large scale changes in the global gene expression patterns of vascular tumors, including alterations in the expression of established cell cycle and apoptotic regulators. Using in vivo tumor models we demonstrate that beta blockade shows remarkable efficacy as a single agent in reducing the growth of angiosarcoma tumors. In summary, these experiments demonstrate the selective cytotoxicity and tumor suppressive ability of beta adrenergic inhibition on malignant vascular tumors and have laid the groundwork for a promising treatment of angiosarcomas in humans.

Propranolol treatment of infantile hemangioma endothelial cells: A molecular analysis.

Infantile hemangiomas (IHs) are non-malignant, largely cutaneous vascular tumors affecting approximately 5-10% of children to varying degrees. During the first year of life, these tumors are strongly proliferative, reaching an average size ranging from 2 to 20 cm. These lesions subsequently stabilize, undergo a spontaneous slow involution and are fully regressed by 5 to 10 years of age. Systemic treatment of infants with the non-selective ß-adrenergic receptor blocker, propranolol, has demonstrated remarkable efficacy in reducing the size and appearance of IHs. However, the mechanism by which this occurs is largely unknown. In this study, we sought to understand the molecular mechanisms underlying the effectiveness of ß blocker treatment in IHs. Our data reveal that propranolol treatment of IH endothelial cells, as well as a panel of normal primary endothelial cells, blocks endothelial cell proliferation, migration, and formation of the actin cytoskeleton coincident with alterations in vascular endothelial growth factor receptor-2 (VEGFR-2), p38 and cofilin signaling. Moreover, propranolol induces major alterations in the protein levels of key cyclins and cyclin-dependent kinase inhibitors, and modulates global gene expression patterns with a particular affect on genes involved in lipid/sterol metabolism, cell cycle regulation, angiogenesis and ubiquitination. Interestingly, the effects of propranolol were endothelial cell-type independent, affecting the properties of IH endothelial cells at similar levels to that observed in neonatal dermal microvascular and coronary artery endothelial cells. This data suggests that while propranolol markedly inhibits hemangioma and normal endothelial cell function, its lack of endothelial cell specificity hints that the efficacy of this drug in the treatment of IHs may be more complex than simply blockage of endothelial function as previously believed.

Histopathological image analysis: a review.

Over the past decade, dramatic increases in computational power and improvement in image analysis algorithms have allowed the development of powerful computer-assisted analytical approaches to radiological data. With the recent advent of whole slide digital scanners, tissue histopathology slides can now be digitized and stored in digital image form. Consequently, digitized tissue histopathology has now become amenable to the application of computerized image analysis and machine learning techniques. Analogous to the role of computer-assisted diagnosis (CAD) algorithms in medical imaging to complement the opinion of a radiologist, CAD algorithms have begun to be developed for disease detection, diagnosis, and prognosis prediction to complement the opinion of the pathologist. In this paper, we review the recent state of the art CAD technology for digitized histopathology. This paper also briefly describes the development and application of novel image analysis technology for a few specific histopathology related problems being pursued in the United States and Europe.

Utility of multispectral imaging for nuclear classification of routine clinical histopathology imagery.

BACKGROUND: We present an analysis of the utility of multispectral versus standard RGB imagery for routine H&E stained histopathology images, in particular for pixel-level classification of nuclei. Our multispectral imagery has 29 spectral bands, spaced 10 nm within the visual range of 420-700 nm. It has been hypothesized that the additional spectral bands contain further information useful for classification as compared to the 3 standard bands of RGB imagery. We present analyses of our data designed to test this hypothesis. RESULTS: For classification using all available image bands, we find the best performance (equal tradeoff between detection rate and false alarm rate) is obtained from either the multispectral or our "ccd" RGB imagery, with an overall increase in performance of 0.79% compared to the next best performing image type. For classification using single image bands, the single best multispectral band (in the red portion of the spectrum) gave a performance increase of 0.57%, compared to performance of the single best RGB band (red). Additionally, red bands had the highest coefficients/preference in our classifiers. Principal components analysis of the multispectral imagery indicates only two significant image bands, which is not surprising given the presence of two stains. CONCLUSION: Our results indicate that multispectral imagery for routine H&E stained histopathology provides minimal additional spectral information for a pixel-level nuclear classification task than would standard RGB imagery.